{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T23:51:26Z","timestamp":1789429886312,"version":"build-2803163510"},"reference-count":25,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T00:00:00Z","timestamp":1767052800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"State Key Laboratory of Advanced Rail Autonomous Operation","award":["RAO2025ZZ006"],"award-info":[{"award-number":["RAO2025ZZ006"]}]},{"name":"Beijing Natural Science Foundation","award":["L221016"],"award-info":[{"award-number":["L221016"]}]},{"name":"Beijing Natural Science Foundation","award":["L241011"],"award-info":[{"award-number":["L241011"]}]},{"name":"Beijing Natural Science Foundation","award":["L251011"],"award-info":[{"award-number":["L251011"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The safe operation of rail transit systems relies heavily on the efficient and reliable maintenance of their equipment, as any malfunction or abnormal operation may pose serious risks to transportation safety. Traditional manual inspection methods are often characterized by high costs, low efficiency, and susceptibility to human error. To address these limitations, this paper presents a rail transit equipment inspection system based on Edge Intelligence (EI) and 5G technology. The proposed system adopts a cloud\u2013edge\u2013end collaborative architecture that integrates Computer Vision (CV) techniques to automate inspection tasks; specifically, a fine-tuned YOLOv8 model is employed for object detection of personnel and equipment, while a ResNet-18 network is utilized for equipment status classification. By implementing an ETSI MEC-compliant framework on edge servers (NVIDIA Jetson AGX Orin), the system enhances data processing efficiency and network performance, while further strengthening security through the use of a 5G private network that isolates critical infrastructure data from the public internet, and improving robustness via distributed edge nodes that eliminate single points of failure. The proposed solution has been deployed and evaluated in real-world scenarios on Beijing Metro Line 6. Experimental results demonstrate that the YOLOv8 model achieves a mean Average Precision (mAP@0.5) of 92.7% \u00b1 0.4% for equipment detection, and the ResNet-18 classifier attains 95.8% \u00b1 0.3% accuracy in distinguishing normal and abnormal statuses. Compared with a cloud-centric architecture, the EI-based system reduces the average end-to-end latency for anomaly detection tasks by 45% (28.5 ms vs. 52.1 ms) and significantly lowers daily bandwidth consumption by approximately 98.1% (from 40.0 GB to 0.76 GB) through an event-triggered evidence upload strategy involving images and short video clips, highlighting its superior real-time performance, security, robustness, and bandwidth efficiency.<\/jats:p>","DOI":"10.3390\/s26010236","type":"journal-article","created":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T14:33:25Z","timestamp":1767191605000},"page":"236","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Edge Intelligence-Based Rail Transit Equipment Inspection System"],"prefix":"10.3390","volume":"26","author":[{"given":"Lijia","family":"Tian","sequence":"first","affiliation":[{"name":"State Key Laboratory of Advanced Rail Autonomous Operation, Beijing Jiaotong University, Beijing 100044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongli","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Advanced Rail Autonomous Operation, Beijing Jiaotong University, Beijing 100044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Zhu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Advanced Rail Autonomous Operation, Beijing Jiaotong University, Beijing 100044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hailin","family":"Jiang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Advanced Rail Autonomous Operation, Beijing Jiaotong University, Beijing 100044, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinjun","family":"Gao","sequence":"additional","affiliation":[{"name":"Signal and Communication Research Institute, China Academy of Railway Sciences Group Co., Ltd., Beijing 100081, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,30]]},"reference":[{"key":"ref_1","unstructured":"Chandran, P. (2022). Train Based Automated Inspection for Railway Fastening System. [Ph.D. Thesis, Lule\u00e5 University of Technology]."},{"key":"ref_2","unstructured":"Wu, Z., Xu, X., Gao, Y., Liang, X., and Cai, C. (2023, January 7\u20138). Intelligent Inspection System of Coal Preparation Plant Based on Dynamic QR Code. Proceedings of the International Conference on 6GN for Future Wireless Networks, Shanghai, China."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"4938","DOI":"10.1109\/JSEN.2020.3030934","article-title":"A simple positioning system for large-scale indoor patrol inspection using foot-mounted INS, QR code control points, and smartphone","volume":"21","author":"Liu","year":"2020","journal-title":"IEEE Sens. J."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1016\/j.rcim.2017.06.005","article-title":"Design and development of an Inspection Robotic System for indoor applications","volume":"49","author":"Rea","year":"2018","journal-title":"Robot. Comput. Integr. Manuf."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"108874","DOI":"10.1016\/j.compeleceng.2023.108874","article-title":"An autonomous rail-road amphibious robotic system for railway maintenance using sensor fusion and mobile manipulator","volume":"110","author":"Liu","year":"2023","journal-title":"Comput. Electr. Eng."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"114274","DOI":"10.1016\/j.measurement.2024.114274","article-title":"A diagnostic method of freight wagons hunting performance based on wayside hunting detection system","volume":"227","author":"Wang","year":"2024","journal-title":"Measurement"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Gong, T., and Zhu, L. (2022, January 4\u20138). Edge Intelligence-based Obstacle Intrusion Detection in Railway Transportation. Proceedings of the GLOBECOM 2022\u20142022 IEEE Global Communications Conference, Rio de Janeiro, Brazil.","DOI":"10.1109\/GLOBECOM48099.2022.10001123"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"7068349","DOI":"10.1155\/2018\/7068349","article-title":"Deep learning for computer vision: A brief review","volume":"2018","author":"Voulodimos","year":"2018","journal-title":"Comput. Intell. Neurosci."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1680","DOI":"10.3390\/make5040083","article-title":"A comprehensive review of yolo architectures in computer vision: From yolov1 to yolov8 and yolo-nas","volume":"5","author":"Terven","year":"2023","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Liu, T. (2020, January 13\u201314). Development and application of electrical equipment intelligent detection management system. Proceedings of the 2020 5th International Conference on Smart Grid and Electrical Automation (ICSGEA), Zhangjiajie, China.","DOI":"10.1109\/ICSGEA51094.2020.00023"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Ranjan, G., Verma, A.K., and Radhika, S. (2019, January 29\u201331). K-nearest neighbors and grid search cv based real time fault monitoring system for industries. Proceedings of the 2019 IEEE 5th International Conference for Convergence in Technology (I2CT), Bombay, India.","DOI":"10.1109\/I2CT45611.2019.9033691"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"85714","DOI":"10.1109\/ACCESS.2020.2991734","article-title":"An overview on edge computing research","volume":"8","author":"Cao","year":"2020","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2647","DOI":"10.1109\/COMST.2024.3393230","article-title":"End-Edge-Cloud Collaborative Computing for Deep Learning: A Comprehensive Survey","volume":"26","author":"Wang","year":"2024","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_14","unstructured":"Ma, H., Wang, P., Qiu, K., Liu, J., and Zhang, Z. (2021). An Intelligent Patrol System Based on Edge Data Center Station. Advances in Wireless Communications and Applications, Proceedings of the 5th ICWCA 2021, Hainan, China, 17\u201319 December 2021, Springer."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"8919","DOI":"10.1109\/TITS.2023.3275741","article-title":"Edge intelligence in intelligent transportation systems: A survey","volume":"24","author":"Gong","year":"2023","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Barbuto, V., Savaglio, C., Chen, M., and Fortino, G. (2023). Disclosing edge intelligence: A systematic meta-survey. Big Data Cogn. Comput., 7.","DOI":"10.3390\/bdcc7010044"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"12027","DOI":"10.1109\/TITS.2021.3109481","article-title":"Smart traffic monitoring system using computer vision and edge computing","volume":"23","author":"Liu","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/MVT.2018.2883777","article-title":"Deep learning for reliable mobile edge analytics in intelligent transportation systems: An overview","volume":"14","author":"Ferdowsi","year":"2019","journal-title":"IEEE Veh. Technol. Mag."},{"key":"ref_19","unstructured":"Peltonen, E., Bennis, M., Capobianco, M., Debbah, M., Ding, A., Gil-Casti\u00f1eira, F., Jurmu, M., Karvonen, T., Kelanti, M., and Kliks, A. (2020). 6G white paper on edge intelligence. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"3212","DOI":"10.1109\/TNNLS.2018.2876865","article-title":"Object detection with deep learning: A review","volume":"30","author":"Zhao","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"624","DOI":"10.1109\/TCCN.2020.3018159","article-title":"Collaborative cloud-edge-end task offloading in mobile-edge computing networks with limited communication capability","volume":"7","author":"Kai","year":"2020","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Rejeb, S.B., and Nasser, N. (2024, January 9\u201313). Optimizing Video Surveillance in IoT 6G with Edge\/Fog Computing. Proceedings of the ICC 2024-IEEE International Conference on Communications, Denver, CO, USA.","DOI":"10.1109\/ICC51166.2024.10622190"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 11\u201314). Identity mappings in deep residual networks. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Koonce, B. (2021). ResNet 50. Convolutional Neural Networks with Swift for Tensorflow: Image Recognition and Dataset Categorization, Apress.","DOI":"10.1007\/978-1-4842-6168-2"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/236\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T05:30:46Z","timestamp":1767245446000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/1\/236"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,30]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26010236"],"URL":"https:\/\/doi.org\/10.3390\/s26010236","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,30]]}}}